meme-creator
Creates video/GIF memes by overlaying images (logos, avatars, stickers) onto moving objects in a clip with frame-accurate tracking, then exports MP4 + GIF
Install / Use
npx skills add daymade/claude-code-skills --skill meme-creatorInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Development & EngineeringSupported Platforms
Our assessment of meme-creator
meme-creator scores 92/100 on our quality scale, 911th of 4,698 Development & Engineering skills we index (top 20%).
Its SKILL.md is 7.0 KB long, well organised into 13 sections with 5 code examples: a thorough specification that gives an agent plenty to work with.
With 1,426 GitHub stars, it is one of the more widely adopted skills in the catalogue.
Maintenance, license and trust
- The repository was last updated about 2 months ago, so meme-creator is actively maintained.
- Our last check on 2026-10-27 found the source still online.
- It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
- Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-10-04. Automated pattern scan on 2026-10-04. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
meme-creator compared with similar skills
All 4 of these similar skills score higher than meme-creator; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| meme-creator (this skill)by daymade | 92 | 1.4k | 53d ago | SKILL.md |
| taste-skillby Leonxlnx | 100 | 116.8k | 8d ago | CLAUDE.md |
| ai-job-searchby ai-job-search-dev | 100 | 72.1k | today | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 47.3k | 2d ago | CLAUDE.md |
| lobehubby lobehub | 100 | 85.6k | today | MCP Server |
Frequently asked questions
- How do I install meme-creator?
- Run
npx skills add daymade/claude-code-skills --skill meme-creator. The install tabs above show the steps for each supported agent. - Which AI agents does meme-creator work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is meme-creator safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is meme-creator still maintained?
- The repository was last updated about 2 months ago, so meme-creator is actively maintained.
Skill content
View source on GitHubname: meme-creator description: >- Creates video/GIF memes by overlaying images (logos, avatars, stickers) onto moving objects in a clip with frame-accurate tracking, then exports MP4 + GIF. Use whenever the user wants a meme, 梗图, 表情包, or reaction GIF from footage; to cover faces in a video; or asks to 把 logo/头像贴到视频里跟着动. Not for transcript-driven editing, programmatic scene generation, or subtitle work.
Meme Creator
Turn a video clip into a meme: images (logos, avatars, stickers) glued onto moving objects so they follow the motion frame by frame, delivered as MP4 + GIF.
The failure mode that ruins this is not tracking drift — it is gluing the wrong person's avatar on screen because a name was bound to the first plausible account found. So step 0 is identity, not tooling.
For a static image meme, skip tracking entirely: put one manual_keys entry
per target ([[1, [x, y, w, h]]]) in the overlays config and render just that
frame — --tracks is optional when every position comes from keys.
Requirements
ffmpegon PATHuv— all bundled Python scripts carry inline dependencies; run them withuv run <script>and deps resolve themselvesyt-dlponly when downloading (uv run --with yt-dlp yt-dlp ...)- Chrome/Chromium only when rasterizing an SVG logo (asset-binding.md)
- Script paths below are written
scripts/…relative to this skill's bundle directory. Resolve the bundle path once (SKILL_DIR=<path to this skill>) and run"$SKILL_DIR"/scripts/make_sheets.py …— your working directory is the scratch dir, not the bundle.
Pipeline
Work inside a scratch directory (/tmp/<meme-name>/ or similar), deliver only
the final MP4 + GIF.
0. Bind identities before fetching assets
When the user names who/what goes on screen ("Codex, Claude, and Tibo's avatar"), every ambiguous name must survive the disambiguation gate in references/asset-binding.md — enumerate candidates with a handle-free search, discriminate from the request context (the peer entities listed alongside are the strongest signal), and ask the user when context cannot decide. That file also covers logo/avatar sourcing, SVG→PNG with real transparency via headless Chrome, and badge styling. Fetch and eyeball every image before compositing it.
1. Acquire the source
Local file: use it. URL: yt-dlp handles bilibili (incl. b23.tv short links),
YouTube, and most sites:
uv run --with yt-dlp yt-dlp -f "bv*+ba/b" --merge-output-format mp4 -o "source.%(ext)s" "<url>"
If a domestic-CN site fails with a proxy tunnel error, retry with --proxy ""
(a local HTTP proxy breaks some domestic CDNs); if an international site times
out, retry with the local proxy.
Check duration: ffprobe -v error -show_entries format=duration -of csv=p=0 source.mp4
2. Locate the segment
Never track "the whole video." Find the exact scene with a 1–2 fps contact sheet, then expand around it:
ffmpeg -v error -ss <start_s> -t 40 -i source.mp4 -vf "fps=1,scale=240:-1,tile=5x8" -frames:v 1 contact.png
Read the sheet, pick the beat boundaries (entrance → action → exit), and cut the final segment ±1 s of padding. Extract the frame sequence at native fps:
mkdir -p seq && ffmpeg -v error -ss <seg_start> -i source.mp4 -t <seg_dur> seq/f_%04d.png
ffprobe -v error -select_streams v:0 -show_entries stream=r_frame_rate -of csv=p=0 source.mp4
3. Prep overlay assets
One image per target, PNG with alpha. Unify mixed assets (app icon + logo mark
- photo avatar) as
circle-whitebadges — see asset-binding.md for why and for the avatar circular-mask handling.
4. Track the targets
Full procedure and failure taxonomy: references/tracking-playbook.md. Short form:
- Grid one frame where all targets are fully visible:
uv run scripts/make_sheets.py grid --frames 'seq/f_%04d.png' --index 30 --out grid.pngand read each target's[x, y, w, h]box off the grid. - Write the tracking config (targets + init frame), run:
uv run scripts/track_boxes.py --frames 'seq/f_%04d.png' --config track.json --out tracks.json --last <N> - Verify:
uv run scripts/make_sheets.py tile --frames 'seq/f_%04d.png' --tracks tracks.json --start 1 --end <N> --step-frames 15 --out verify.pngand look at every tile. - Fix what the tiles show: re-anchor later segments (shot changes, scale
blowups, drift), or take over a smooth long shot with
manual_keys. Expect 2–3 rounds. Then markvisible/fade_in/fade_outfor every exit, entrance, and empty-stretch — a logo parked on an empty frame is the most visible possible bug.
5. Render
uv run scripts/render_overlay.py --frames 'seq/f_%04d.png' --tracks tracks.json \
--overlays overlays.json --out 'out/o_%04d.png' --last <N>
Spot-check a rendered contact sheet (make_sheets.py tile over out/) before
encoding — much cheaper than re-encoding.
6. Encode + size budget
scripts/encode_outputs.sh --frames 'out/o_%04d.png' --fps <native_fps> \
--source source.mp4 --ss <seg_start> --t <seg_dur> --mp4 meme.mp4 \
--gif meme.gif --gif-width 400 --gif-fps 10 --gif-colors 96
GIF size is driven by frame count × dither noise, not palette size. To fit a
~10 MB chat-app budget, lower knobs in this order: --gif-fps (15→12→10),
then --gif-width (480→400), then --gif-colors (128→96).
7. Verify the encoded deliverables, then deliver
Extract frames from the final MP4 and the final GIF (ffmpeg -ss <t> -frames:v 1) and look at them — the earlier checks verified intermediates;
this one verifies what the recipient will actually see. Deliver both files by
their exact paths.
Troubleshooting
| Symptom | Cause | Fix |
|---|---|---|
| yt-dlp: Tunnel connection failed 503 on a domestic site | local HTTP proxy intercepting | add --proxy "" |
| cairosvg/svglib crash: no library called cairo | missing system cairo | rasterize SVG via headless Chrome (asset-binding.md) |
| Tracker dies exactly at a shot change | CSRT cannot cross cuts | new segments entry at the new shot's first frame |
| Box drifts slowly off the target over ~1 min | template pollution | re-anchor with the tracker's own last-good box, or manual_keys |
| Logo parked mid-frame after subject exits | missing visibility window | fade_out before the exit, no visible range after |
| GIF massively over budget | dither noise × frames | lower --gif-fps first, then width, then colors |
| Logo looks fine in PNGs but wrong in the GIF | checked intermediates only | always verify frames from the encoded file (step 7) |
| Encode fails: Failed to set value '1:a' for option 'map' | source clip has no audio stream | the bundled script maps 1:a? (optional); if running ffmpeg by hand, do the same or drop --source |
References
- references/asset-binding.md — identity disambiguation gate, logo/avatar sourcing, transparency, badge styling
- references/tracking-playbook.md — CSRT failure taxonomy, re-anchor recovery, manual keyframes, fades, verify loop
Related Skills
taste-skill
116.8kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
ai-job-search
72.1kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
47.3kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
lobehub
85.6k🤯 LobeHub - Super-Agents on Your Team. Add super-agents to the chats your team already uses.They take on work by themselves and get better every week.
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
